Skip to main content

Table 3 Area under the ROC curve (AUC) for few optimized SVM classifiers.

From: VirulentPred: a SVM based prediction method for virulent proteins in bacterial pathogens

Modules developed

Sensitivity (%)

Specificity (%)

Accuracy (%)

MCC

AUC under the ROC curve

AAC (Sigmoid kernel)

63.4

75.0

69.2

0.39

0.75

AAC (Linear kernel)

64.5

74.4

69.4

0.39

0.75

AAC (Polynomial kernel)

63.4

75.8

69.6

0.40

0.76

AAC (RBF kernel)

70.0

74.1

72.1

0.44

0.79

Dipeptide Composition (i+1)

70.0

72.3

71.1

0.42

0.79

Dipeptide Composition (i+2)

70.2

73.7

72.0

0.44

0.79

PSSM-profiles

78.1

78.1

78.1

0.56

0.85

Cascade classifier

82.0

81.5

81.8

0.64

0.86